ヒストグラム¶

データのばらつきを見たい場合は，ヒストグラムを利用します．

環境構築¶

# Notebook初期設定
%matplotlib inline
%config InlineBackend.figure_format = 'retina'

import warnings
warnings.filterwarnings('ignore')

import os
import pandas as pd
import plotly.express as px

DIR_IN = '../data/preprocess/out'
FN_WJ = 'wj.csv'

RENDERER = 'plotly_mimetype+notebook'

def show_fig(fig):
    """Jupyter Bookでも表示可能なようRendererを指定"""
    fig.show(renderer=RENDERER)

df = pd.read_csv(os.path.join(DIR_IN, FN_WJ))

df.head(2).T

df_tmp = df.groupby('datePublished')['editor'].first().reset_index()

fig = px.histogram(df_tmp, x='editor')
show_fig(fig)

fig = px.histogram(df, x='')
show_fig(fig)